Improving Large Language Model Safety with Contrastive Representation Learning

Samuel Simko, Mrinmaya Sachan, Bernhard Schölkopf, Zhijing Jin 0001. Improving Large Language Model Safety with Contrastive Representation Learning. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 28166-28194, Association for Computational Linguistics, 2025. [doi]

Authors

Samuel Simko

This author has not been identified. Look up 'Samuel Simko' in Google

Mrinmaya Sachan

This author has not been identified. Look up 'Mrinmaya Sachan' in Google

Bernhard Schölkopf

This author has not been identified. Look up 'Bernhard Schölkopf' in Google

Zhijing Jin 0001

This author has not been identified. Look up 'Zhijing Jin 0001' in Google